InfuserKI: Enhancing Large Language Models with Knowledge Graphs via Infuser-Guided Knowledge Integration

TL;DR

This paper introduces InfuserKI, a framework that enhances large language models by efficiently integrating unknown domain knowledge from knowledge graphs while preventing the forgetting of existing knowledge, leading to improved performance.

Contribution

The paper presents a novel method for integrating unknown knowledge into LLMs using transformer states, reducing knowledge forgetting and outperforming existing baselines.

Findings

Reduces knowledge forgetting by 9% and 6% on benchmark datasets.

Successfully integrates new domain knowledge into LLMs.

Outperforms state-of-the-art baselines in knowledge integration tasks.

Abstract

Large Language Models (LLMs) have achieved exceptional capabilities in open generation across various domains, yet they encounter difficulties with tasks that require intensive knowledge. To address these challenges, methods for integrating knowledge have been developed, which augment LLMs with domain-specific knowledge graphs through external modules. These approaches, however, face data inefficiency issues as they necessitate the processing of both known and unknown knowledge for fine-tuning. Thus, our research focuses on a novel problem: efficiently integrating unknown knowledge into LLMs without unnecessary overlap of known knowledge. A risk of introducing new knowledge is the potential forgetting of existing knowledge. To mitigate this risk, we propose the innovative {\method} framework. This framework employs transformer internal states to determine when to enrich LLM outputs with additional information, effectively preventing knowledge forgetting. Performance evaluations using the UMLS-2.5k and MetaQA domain knowledge graphs reveal that {\method} not only successfully integrates new knowledge but also outperforms state-of-the-art baselines, reducing knowledge forgetting by 9\% and 6\%, respectively.